v1.2.3

What's Changed

• fix: Pass PyTorch device through to AtomScaling by @PascalSalzbrenner in #146
• fix: move tensors to correct device in batch_to_dict by @yanghan234 in #147
• fix: use np.int64 for pbc arrays to fix Cython dtype mismatch by @yanghan234 in #149
• CI: trim build workflow matrix and collapse build+test by @Copilot in #148
• test: add MD ensemble tests and si_diamond_cubic fixture by @yanghan234 in #150
• fix: correct MPS execution on apple silicon by @yanghan234 in #145
• feat: add workflow for BTE thermal conductivity by @yanghan234 in #151
• feat: add verbose option to Relaxer.relax by @yanghan234 in #152
• fix: make MatterSimCalculator picklable by @yanghan234 in #153

New Contributors

• @PascalSalzbrenner made their first contribution in #146
• @Copilot made their first contribution in #148

Full Changelog: v1.2.2...v1.2.3

v1.2.2

What's Changed

• fix stress import import by @danielzuegner in #143

New Contributors

• @danielzuegner made their first contribution in #143

Full Changelog: v1.2.1...v1.2.2

v1.2.1

What's Changed

• Fix ASE 3.27 compatibility: update Filter import and optimizer API by @yanghan234 in #139
• fix: fixing import failure with setuptools>=82 by @yanghan234 in #141

Full Changelog: v1.2.0...v1.2.1

v1.2.0

🚀 Features & Enhancements

• BatchRelaxer: Added max_n_steps argument for greater flexibility (#90, @ClaudioZeni)
• Benchmark Datasets: Released in-house compiled benchmark datasets (#105, @yanghan234)
• Packaging:
  • Updated packaging to use a temporary directory (#109, @bi-ran)
  • Packaging now runs within a context manager for improved reliability (#110, @bi-ran)

🐛 Bug Fixes

• Fixed valid path handling in finetune (#106, @ZeroKnighting)
• Fixed bug with nsteps not working properly (#101, @ClaudioZeni)

🛠️ Maintenance & CI

• Upgraded to NumPy 2 (#120, @CompRhys)
• Dropped support for Python 3.9 (#121, @yanghan234)
• CI improvements:
  • Updated cibuildwheel configuration (#122, @yanghan234)
  • Removed Python 3.9 from cibuildwheel (#123, @yanghan234)

🧹 Other Changes

• Fixed typos (#114, @co63oc)

🙌 New Contributors

• @co63oc made their first contribution (#114)
• @CompRhys made their first contribution (#120)

Full Changelog: v1.1.2...v1.2.0

---

v1.1.2

What's Changed

• feat: add taut option to commandline by @yanghan234 in #92
• Unpin torch<2.5.0 by @janosh in #89
• ci: Update python-publish.yaml by @yanghan234 in #93
• ci: Update python-publish.yaml by @yanghan234 in #94

Full Changelog: v1.1.1...v1.1.2

What's Changed

• feat: add taut option to commandline by @yanghan234 in #92
• Unpin torch<2.5.0 by @janosh in #89
• ci: Update python-publish.yaml by @yanghan234 in #93
• ci: Update python-publish.yaml by @yanghan234 in #94

Full Changelog: v1.1.1...v1.1.2

v1.1.2rc3

What's Changed

• feat: add taut option to commandline by @yanghan234 in #92
• Unpin torch<2.5.0 by @janosh in #89
• ci: Update python-publish.yaml by @yanghan234 in #93
• ci: Update python-publish.yaml by @yanghan234 in #94

Full Changelog: v1.1.1...v1.1.2rc3

v1.1.2rc2

What's Changed

• feat: add taut option to commandline by @yanghan234 in #92
• Unpin torch<2.5.0 by @janosh in #89
• ci: Update python-publish.yaml by @yanghan234 in #93

Full Changelog: v1.1.1...v1.1.2rc2

v1.1.2rc1

What's Changed

• feat: add taut option to commandline by @yanghan234 in #92
• Unpin torch<2.5.0 by @janosh in #89

Full Changelog: v1.1.1...v1.1.2rc1

v1.1.1

What's Changed

• mlflow packaging script + compatibility changes by @bi-ran in #85
• pin mattersim dependency for mlflow by @bi-ran in #86
• Feat: Add option to turn off calculating phonon spectrum and phonon density of states by @mbagheri20 in #87
• Fix: make box smaller for no pbc structure by @anyangml in #84

New Contributors

• @bi-ran made their first contribution in #85
• @mbagheri20 made their first contribution in #87
• @anyangml made their first contribution in #84

Full Changelog: v1.1.0...v1.1.1

v1.1.0

What's Changed

New Features

• 🔥 Add finetune method for MatterSim by @brian-xue in #68 and @ZeroKnighting in #71
• 🔥 Add CLI scripts to quickly invoke calculations in commandline by @yanghan234 in #69
• 🔥 Add batch relaxation script by @ClaudioZeni in #73

Documentation

• Add finetune docs by @ZeroKnighting in #78
• Update finetune.rst by @yanghan234 in #80
• Add batch relax docs by by @ClaudioZeni in #75

Fixes

• Fix cutoff auto-detect in calculate by @ZeroKnighting in #62
• Fix finetune error with CPU device by @ZeroKnighting in #76
• Update phonon.py to save phonon eigenvectors by @yanghan234 in #77

Dependencies

• Update dependencies by @yanghan234 in #67
• Remove emmet-core down-pin causing ecosystem clash by @janosh in #61

Continuous Integration

• Update workflows by @yanghan234 in #72

Full Changelog: v1.0.0...v1.1.0